{"benchmark_id":"agieval","name":"AGIEval","parent_benchmark":null,"categories":["math","reasoning","legal","general"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"A human-centric benchmark for evaluating foundation models on standardized exams including college entrance exams (Gaokao, SAT), law school admission tests (LSAT), math competitions, lawyer qualification tests, and civil service exams. Contains 20 tasks (18 multiple-choice, 2 cloze) designed to assess understanding, knowledge, reasoning, and calculation abilities in real-world academic and professional contexts.","paper_link":"https://arxiv.org/abs/2304.06364","implementation_link":"https://github.com/ruixiangcui/AGIEval","verified":false,"created_at":"2026-05-07T16:53:21.415820+00:00","updated_at":"2026-07-05T18:27:42.150875+00:00","statistics":{"total_models":10,"average_score":0.53098,"min_score":0.285,"max_score":0.658,"score_stddev":0.10511350267422565,"verified_count":0,"self_reported_count":10},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"mistral-small-24b-base-2501","model_name":"Mistral Small 3 24B Base","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.658,"normalized_score":0.658,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/mistralai/Mistral-Small-24B-Base-2501","analysis_method":"-","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-01-30","param_count":23600000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"ministral-3-14b-base-2512","model_name":"Ministral 3 (14B Base 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.648,"normalized_score":0.648,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-04","param_count":14000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"ministral-3-8b-base-2512","model_name":"Ministral 3 (8B Base 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.591,"normalized_score":0.591,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-04","param_count":8000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"hermes-3-70b","model_name":"Hermes 3 70B","organization_id":"nous-research","organization_name":"Nous Research","organization_country":"US","score":0.5618,"normalized_score":0.5618,"verified":false,"self_reported":true,"self_reported_source":"https://nousresearch.com/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-15","param_count":70000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"gemma-2-27b-it","model_name":"Gemma 2 27B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.551,"normalized_score":0.551,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/blog/gemma2","analysis_method":"3-5-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-06-27","param_count":27200000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"gemma-2-9b-it","model_name":"Gemma 2 9B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.528,"normalized_score":0.528,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/blog/gemma2","analysis_method":"3-5-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-06-27","param_count":9240000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":7,"model_id":"ministral-3-3b-base-2512","model_name":"Ministral 3 (3B Base 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.511,"normalized_score":0.511,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-04","param_count":3000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"granite-3.3-8b-base","model_name":"Granite 3.3 8B Base","organization_id":"ibm","organization_name":"IBM","organization_country":"US","score":0.493,"normalized_score":0.493,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/ibm-granite/granite-3.3-8b-base","analysis_method":"Score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-04-16","param_count":8170000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":9,"model_id":"ministral-8b-instruct-2410","model_name":"Ministral 8B Instruct","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.483,"normalized_score":0.483,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/mistralai/Ministral-8B-Instruct-2410","analysis_method":"-","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-10-16","param_count":8019808256,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":10,"model_id":"ernie-4.5","model_name":"ERNIE 4.5","organization_id":"baidu","organization_name":"Baidu","organization_country":"CN","score":0.285,"normalized_score":0.285,"verified":false,"self_reported":true,"self_reported_source":"https://cloud.baidu.com/doc/WENXINWORKSHOP/s/clntwmv7t","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-25","param_count":21000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}